© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7014
    Prev
    Next
    INDEX
    Explanations

    the letter "V" or the Cyrillic letter "В"

    oai_token-act-pair · gemini-2.0-flash

    code/equations/foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.69
    InjectAttribute
    -0.68
    новништво
    -0.65
     >=",
    -0.61
    Datuak
    -0.61
    Personendaten
    -0.60
     BoxDecoration
    -0.59
    });*/
    -0.57
    InstrumentedTest
    -0.55
     StatelessWidget
    -0.53
    POSITIVE LOGITS
    Portály
    0.66
     везе
    0.56
    ConstraintMaker
    0.53
    ransition
    0.49
    SequentialGroup
    0.48
    leste
    0.48
    orithmic
    0.48
    ebbe
    0.47
     libur
    0.47
    rolle
    0.46
    Activations Density 0.924%

    No Known Activations